Dynamic Optimization in 5G Network Slices: A Comparative Study of Whale Optimization, Particle Swarm Optimization, and Genetic Algorithm-Reference-Cited by-同舟云学术

Dynamic Optimization in 5G Network Slices: A Comparative Study of Whale Optimization, Particle Swarm Optimization, and Genetic Algorithm

Published:2024-07-30 Issue:3 Volume:12 Page:849-862
ISSN:2347-470X
Container-title:International Journal of Electrical and Electronics Research
language:en
Short-container-title:IJEER

Author:

Okindo Geoffrey¹,Kamucha Prof. George²,Oyie Dr. Nicholas³

Affiliation:

1. Student, Pan African University Institute for Basic Sciences, Technology, and Innovation, Nairobi

2. Prof, University of Nairobi, Nairobi

3. Dr, Murang’a University of Technology, Nairobi

Abstract

This study presents a comprehensive framework for optimizing 5G network slices using metaheuristic algorithms, focusing on Enhanced Mobile Broadband (eMBB), Ultra-Reliable Low-Latency Communications (URLLC), and massive Machine Type Communications (mMTC) scenarios. The initial setup involves a MATLAB-based 5G New Radio (NR) Physical Downlink Shared Channel (PDSCH) simulation and OpenAir-Interface (OAI) 5G network testbed, utilizing Ubuntu 22.04 Long Term Support (LTS), MicroStack, Open-Source MANO (OSM), and k3OS to create a versatile testing environment. Key network parameters are identified for optimization, including power control settings, signal-to-noise ratio targets, and resource block allocation, to address the unique requirements of different 5G use cases. Metaheuristic algorithms, specifically the Whale Optimization Algorithm (WOA), Particle Swarm Optimization (PSO), and Genetic Algorithm (GA), are employed to optimize these parameters. The algorithms are assessed based on their ability to enhance throughput, reduce latency, and minimize jitter within the network slices and the MATLAB simulation model. Each algorithm’s performance is evaluated through iterative testing, with improvements measured against established pre-optimization benchmarks. The results demonstrate significant enhancements in network performance post-optimization. For eMBB, the GA shows the most substantial increase in throughput, while PSO is most effective in reducing latency for URLLC applications. In mMTC scenarios, GA achieves the most notable reduction in jitter, illustrating the potential of metaheuristic algorithms in fine-tuning 5G networks to meet diverse service requirements. The study concludes that the strategic application of these algorithms can significantly improve the efficiency and reliability of 5G network slices, offering a scalable approach to managing the complex dynamics of next-generation wireless networks.

Publisher

FOREX Publication

Reference20 articles.

1. P. Popovski, K. F. Trillingsgaard, O. Simeone, and G. Durisi, “5G wireless network slicing for eMBB, URLLC, and mMTC: A communication-theoretic view,” Ieee Access, vol. 6, pp. 55765–55779, 2018.

2. L. A. Freitas et al., “Slicing and Allocation of Transformable Resources for the Deployment of Multiple Virtualized Infrastructure Managers (VIMs),” in 2018 4th IEEE Conference on Network Softwarization and Workshops (NetSoft), 2018, pp. 424–432. doi: 10.1109/NETSOFT.2018.8459990.

3. H. Zhang, N. Liu, X. Chu, K. Long, A.-H. Aghvami, and V. C. M. Leung, “Network slicing based 5G and future mobile networks: Mobility, resource management, and challenges,” IEEE Communications Magazine, vol. 55, no. 8, pp. 138–145, 2017.

4. S. Mirjalili and A. Lewis, “The whale optimization algorithm,” Advances in engineering software, vol. 95, pp. 51–67, 2016.

5. H. Qu, B. Zhang, Z. Duan, and Y. Zhang, “Network Slice Resource Mapping Method Based on Discrete Binary Particle Swarm Optimization Algorithm,” in 2020 IEEE International Conference on Artificial Intelligence and Information Systems (ICAIIS), 2020, pp. 412–416.